added gsm_plus (#2103)

* added gsm_plus

* formatted dataset to have train-test-splits

* README.md for gsm-plus

* Update README.md

* GSM-Plus: added gsm_plus_mini

* GSM-Plus: attribution to original dataset

* Update README.md

* Update README.md

* Update README.md

---------
Co-authored-by: Lintang Sutawika <lintang@eleuther.ai>

lm_eval/tasks/gsm_plus/README.md

+# gsm_plus
+
+### Paper
+
+Title: `GSM-PLUS: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers`
+
+Abstract: `Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathematical knowledge or merely rely on shortcuts for mathematical reasoning. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs’ math reasoning capability by testing a wide range of question variations. We introduce the adversarial grade school math (GSM-PLUS) dataset, an extension of GSM8K augmented with various mathematical perturbations. Our experiments on 25 LLMs and 4 prompting techniques show that while LLMs exhibit different levels of math reasoning abilities, their performances are far from robust. In particular, even for problems that have been solved in GSM8K, LLMs can make mistakes when new statements are added or the question targets are altered. We also explore whether more robust performance can be achieved by composing existing prompting methods, in which we try an iterative method that generates and verifies each intermediate thought based on its reasoning goal and calculation result.`
+
+Note: the original GSM-Plus dataset lacks a train-test split. To facilitate format compatibility with GSM 8k, the dataset is split with a test ratio of 0.1 (after shuffling).
+
+Homepage (original): https://huggingface.co/datasets/qintongli/GSM-Plus
+Homepage (preprocessed): https://huggingface.co/datasets/sjyuxyz/GSM-Plus-Formatted
+
+### Citation
+
+```bibtex
+@misc{li2024gsmpluscomprehensivebenchmarkevaluating,
+      title={GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers},
+      author={Qintong Li and Leyang Cui and Xueliang Zhao and Lingpeng Kong and Wei Bi},
+      year={2024},
+      eprint={2402.19255},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2402.19255},
+}
+```
+
+### Groups and Tasks
+
+#### Groups
+
+* Not part of a group yet
+
+#### Tasks
+
+The following tasks evaluate subjects in the gsm_plus dataset
+- `gsm_plus`
+- `gsm_plus_mini`
+
+### Checklist
+
+For adding novel benchmarks/datasets to the library:
+* [x] Is the task an existing benchmark in the literature?
+  * [x] Have you referenced the original paper that introduced the task?
+  * [x] If yes, does the original paper provide a reference implementation? If so, have you checked against the reference implementation and documented how to run such a test?
+
+
+If other tasks on this dataset are already supported:
+* [ ] Is the "Main" variant of this task clearly denoted?
+* [ ] Have you provided a short sentence in a README on what each new variant adds / evaluates?
+* [ ] Have you noted which, if any, published evaluation setups are matched by this variant?

lm_eval/tasks/gsm_plus/gsm_plus.yaml

+tag:
+  - math_word_problems
+task: gsm_plus
+dataset_path: qintongli/GSM-Plus
+dataset_name: all
+output_type: generate_until
+training_split: test
+fewshot_split: test
+test_split: test
+doc_to_text: "Question: {{question}}\nAnswer:"
+doc_to_target: "{{solution}}"
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: false
+    regexes_to_ignore:
+      - ","
+      - "\\$"
+      - "(?s).*#### "
+      - "\\.$"
+generation_kwargs:
+  until:
+    - "Question:"
+    - "</s>"
+    - "<|im_end|>"
+  do_sample: false
+  temperature: 0.0
+repeats: 1
+num_fewshot: 5
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "#### (\\-?[0-9\\.\\,]+)"
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: "regex"
+        group_select: -1
+        regex_pattern: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
+      - function: "take_first"
+metadata:
+  version: 1.0

lm_eval/tasks/gsm_plus/gsm_plus_mini.yaml

+tag:
+  - math_word_problems
+task: gsm_plus_mini
+dataset_path: qintongli/GSM-Plus
+dataset_name: all
+output_type: generate_until
+training_split: testmini
+fewshot_split: testmini
+test_split: testmini
+doc_to_text: "Question: {{question}}\nAnswer:"
+doc_to_target: "{{solution}}"
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: false
+    regexes_to_ignore:
+      - ","
+      - "\\$"
+      - "(?s).*#### "
+      - "\\.$"
+generation_kwargs:
+  until:
+    - "Question:"
+    - "</s>"
+    - "<|im_end|>"
+  do_sample: false
+  temperature: 0.0
+repeats: 1
+num_fewshot: 5
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "#### (\\-?[0-9\\.\\,]+)"
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: "regex"
+        group_select: -1
+        regex_pattern: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
+      - function: "take_first"
+metadata:
+  version: 1.0